[论文解读] Low-Latency Broadband Analog Aggregation for Federated Edge Learning.

Guangxu Zhu, Yong Wang+1 more|arXiv (Cornell University)|Dec 30, 2018

Privacy-Preserving Technologies in Data参考文献 24被引用 47

一句话总结

本文提出在联邦边缘学习中采用模拟空中聚合，通过利用多址信道叠加特性，实现设备数量增长下的近似线性延迟降低，从而减少通信延迟。通过支持同时模型更新传输与模拟聚合，该方法优于传统OFDMA方案，尤其在高移动性环境下结合机会调度时表现更优。

ABSTRACT

The popularity of mobile devices results in the availability of enormous data and computational resources at the network edge. To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low latency multi-access scheme for edge learning. We consider a popular framework, federated edge learning (FEEL), where edge-server and on-device learning are synchronized to train a model without violating user-data privacy. It is proposed that model updates simultaneously transmitted by devices over broadband channels should be analog aggregated over-the-air by exploiting the superposition property of a multi-access channel. Thereby, interference is harnessed to provide fast implementation of the model aggregation. This results in dramatical latency reduction compared with the traditional orthogonal access (i.e., OFDMA). In this work, the performance of FEEL is characterized targeting a single-cell random network. First, due to power alignment between devices as required for aggregation, a fundamental tradeoff is shown to exist between the update-reliability and the expected update-truncation ratio. This motivates the design of an opportunistic scheduling scheme for FEEL that selects devices within a distance threshold. This scheme is shown using real datasets to yield satisfactory learning performance in the presence of high mobility. Second, both the multi-access latency of the proposed analog aggregation and the OFDMA scheme are analyzed. Their ratio, which quantifies the latency reduction of the former, is proved to scale almost linearly with device population.

研究动机与目标

• 解决尽管计算速度快速提升，边缘学习中日益严重的通信延迟瓶颈问题。
• 通过支持多个设备模型更新的同时并行传输，克服正交多址接入（如OFDMA）在联邦边缘学习中的局限性。
• 设计一种利用信道叠加特性的低延迟多址方案，实现模型更新的模拟聚合，同时不损害隐私。
• 基于设备距离设计一种机会调度方案，以在高移动性环境中平衡更新可靠性与截断比率。
• 在单小区随机网络设置下，表征并量化模拟聚合相较于OFDMA的延迟降低程度。

提出的方法

• 利用多址衰落信道的叠加特性，实现多个设备同时传输的模型更新的模拟聚合。
• 通过设备间功率对齐，确保边缘服务器接收到的叠加信号对应于有意义的模型更新聚合结果。
• 提出一种机会调度方案，选择在预设距离阈值内的设备，以优化更新可靠性与截断比率之间的权衡。
• 分析所提出的模拟聚合与传统OFDMA方案的多址延迟，以量化性能增益。
• 推导模拟聚合与OFDMA之间的延迟降低比率，证明其几乎随设备数量线性增长。
• 使用真实世界数据集验证该方法，证明其在高移动性条件下的鲁棒性。

实验结果

研究问题

• RQ1 在联邦边缘学习中，通过信道叠加实现的模拟空中聚合与传统OFDMA相比，在通信延迟方面表现如何？
• RQ2 由于模拟聚合中需进行功率对齐，其在更新可靠性与期望更新截断比率之间存在何种根本性权衡？
• RQ3 机会调度如何在高移动性边缘环境中提升学习性能，同时保持低延迟？
• RQ4 模拟聚合的延迟降低程度在多大程度上随参与设备数量而扩展？
• RQ5 在真实的单小区网络环境中，设备移动性对模拟聚合性能有何影响？

主要发现

• 所提出的模拟聚合方案在设备数量增加时，实现与OFDMA相比近乎线性的延迟降低扩展。
• 由于模拟聚合中必须进行功率对齐，建立了更新可靠性与期望更新截断比率之间的根本性权衡。
• 基于距离阈值的机会调度方案即使在高移动性条件下，也能实现令人满意的训练性能，经真实数据集验证。
• 证明了模拟聚合与OFDMA之间的延迟降低比率几乎随设备数量线性增长。
• 使用空中模拟聚合显著降低了通信延迟，相较于正交接入方式，使其适用于低延迟边缘学习应用。
• 该方法在实现设备间快速、同步的模型聚合的同时，保持了用户数据隐私。